Kubb is a modular code-generation framework that turns OpenAPI descriptions into type-safe TypeScript code, Zod schemas, and TanStack Query integrations. It is used by TypeScript developers to generate client code and related interfaces from API specifications. The catalogue contains extensions such as skills, commands, hooks, agents, and a plugin that support Kubb workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kubb-labs/kubb --skill outputgit clone --depth 1 https://github.com/kubb-labs/kubbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kubb-labs/kubb/output)<a href="https://agentmods.dev/skills/kubb-labs/kubb/output"><img src="https://agentmods.dev/badge/skills/kubb-labs/kubb/output/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kubb-labs/kubb/output"><img src="https://agentmods.dev/badge/skills/kubb-labs/kubb/output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00557 |
| Opus 5.5 | $0.00014 | $0.00223 |
| Sonnet 5.5 | $0.00007 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
output scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Skill
This skill instructs agents on importing and using the code Kubb generates from an OpenAPI/Swagger spec.
When to Use
- Writing application code that calls the generated client or hooks
- Writing tests that use the generated mocks or schemas
- Wiring generated files into an app
What It Does
- Explains where generated code lands
- Shows how to discover the real exports and a plugin's options
- Lists the rules for keeping generated code in sync
Where output lands
Kubb writes generated code under the output.path from kubb.config.ts (for example ./src/gen),
organized into the folders each plugin sets through its own output.path (for example models,
clients, hooks). Generated files carry a Do not edit manually banner and are rewritten on
every kubb generate, so change them by editing the spec or config and regenerating.
Export names derive from the spec's operationId and schema names. Casing and grouping are
configurable, so read the generated files for the exact names and signatures rather than assuming
them.
Find what was generated
Inspect the real output instead of guessing:
- Read
kubb.config.tsfor the top-leveloutput.pathand each plugin'soutput.path. - List the output directory for the actual file and export names.
- Read an installed plugin's
Optionstype (node_modules/@kubb/plugin-<name>/src/types.tsor the published type declarations) for its options and defaults, and the plugin's docs page (https://kubb.dev/extensions/kubb-labs/plugin-<name>) for dependencies. Use those as the source of truth rather than assuming an option name.
Import from a folder's index.ts when output.barrel is set, otherwise import the file directly.
Rules
- Never edit files under
output.path. Edit the spec or config and rerunkubb generate. - Import generated code instead of copying it, so a regenerate keeps callers in sync.
- Configure the runtime client once. The client functions and framework hooks share it.
- Typecheck after regenerating so a spec change that broke a call site shows up.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 36529a8f4d00
- 1mo ago First seen · 59 lines · 35 tokens per session scan A 82d9ae7eed40
output is a skill published in the GitHub repository kubb-labs/kubb (1,825 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 557 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skmtc-architecture
Understand what Skmtc is, how its engine works, and the architectural invariants — for agents building or extending infrastructure around Skmtc rather than authoring generators or running the CLI. Covers the three-phase pipeline, the host/Worker boundary, cross-generator coordination, the manifest, the attribution /…
skmtc-debug
Diagnose failures in Skmtc sessions — no output, wrong output, error messages, failed bundle builds, parseIssues, "Registered definition mismatch", ref cycles, "Module not found" in generated code, or any other broken behavior. Applies across both CLI usage and generator authoring contexts. Use this skill when the…
skmtc-lang-kotlin
The Kotlin target-language layer for Skmtc generators (@skmtc/lang-kotlin): base factories, KtSnippet, the seven entity kinds, packages-from-paths imports, the head+value render model, KtAnnotation and the composition classes, sanitization and @SerialName placement, plus the current-API worked example (the shipped…
skmtc-retro-review
Aggregate friction log files across a time period to identify recurring patterns, classify each cluster by intervention type, produce a prioritized action plan with success criteria, and calculate convergence metrics. Complements skmtc-retro (which captures per-session signal) by acting as the system's actuator…
skmtc-retro
Run a self-retrospective on a Skmtc-related session — generator authoring, CLI configuration, debugging, or any sustained interaction involving @skmtc/core, @skmtc/cli, or @skmtc/gen- packages. Captures three distinct outputs: (1) friction entries (mistakes, surprises, overridden defaults, multi-cycle struggles), (2)…
skmtc-generator
Author and edit Skmtc generators — packages that project an OpenAPI domain model into application code. Method: clone the nearest stock generator, then apply the engine rules imitation can't teach. Assumes zero prior Skmtc knowledge. Use when asked to "write a skmtc generator", "author/clone/customize gen-x", "add a…